© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2071
    Prev
    Next
    INDEX
    Explanations

    references to planning or actions taken prior to an event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gem
    -0.67
     rooft
    -0.64
     protagonists
    -0.63
    izoph
    -0.58
     creators
    -0.58
    ellar
    -0.57
    lez
    -0.56
    kamp
    -0.55
     adolesc
    -0.55
     adversaries
    -0.55
    POSITIVE LOGITS
    ector
    0.75
     Mehran
    0.75
    of
    0.74
    osis
    0.68
    UGE
    0.63
    andum
    0.63
    ography
    0.62
    oshop
    0.61
    orus
    0.61
     of
    0.61
    Activations Density 0.025%

    No Known Activations